Target Pattern Research Articles

A Fast and Efficient Beamforming Algorithm Imitating Plant Growth Gene for Phased Array Antenna

In this paper, a new beamforming algorithm for phased array antennas is proposed, the plant growth gene algorithm. The algorithm consists of three steps. Firstly, according to the excitation relation of the array unit before and after the local fine-tuning of the antenna radiation pattern, the model for solving the array unit excitation difference is established. Secondly, the Taylor series expansion is used to solve the model, and the growth model is established based on this, and the beam tuning network is designed to realize the growth model. Finally, based on the growth gene obtained by the neural network algorithm, the growth model is called multiple times for high-precision beamforming. This algorithm converts the complex optimization process of array antenna excitation by the classical optimization algorithm into a simple process of fine-tuning the gain at any angle on the beam to make it grow and approach the target pattern. The growth gene is used to weigh the target angle and gain to achieve beamforming, which greatly reduces the complexity of the algorithm and improves its accuracy of the algorithm. Taking a 1 × 16 linear array as an example, a cosecant square beam pattern with a coverage range of −31° to 31° and a maximum gain direction of 17° is designed using the algorithm proposed in this paper. The experimental results show that the proposed algorithm can easily fine-tune the gain of any angle to achieve precise beamforming. Importantly, the growth genes trained by the algorithm are universal to the phased array antenna with the same topology.

Development of Energy Saving Operation Technology for Punctuality and Ride Comfort by Optimizing the Point of Target Pattern Re-Creation

Development of Energy Saving Operation Technology for Punctuality and Ride Comfort by Optimizing the Point of Target Pattern Re-Creation

Electrocardiogram signal patterns detection of myocardial ischemia rhythm using an artificial neural network based on MATLAB/Simulink

This study aims to design a computer program to detect myocardial ischemic heart defects through electrocardiogram (ECG) signal patterns and their accuracy. Myocardial ischemia is a heart disorder caused by the narrowing of the blood vessels in the walls of the heart. The method used is a backpropagation-based artificial neural network (ANN) based on MATLAB/Simulink. The input data is trained to recognize the target pattern of the ECG signal based on the potential and time in the ST segment. The optimal weight of the results of the ANN backpropagation algorithm is used in the process of testing the ECG signal pattern to obtain the ANN output. The ANN output was analyzed for potential depression or elevation to identify normal heart or myocardial ischemia. The results of the training show that from several architectures that have been tested, the optimal ANN architecture is 1 hidden layer with 11 hidden units. These results are obtained from the epoch parameter and the mean square error (MSE) value as well as the accuracy of each architecture. The backpropagation ANN learning process requires 8 epochs to achieve the performance goal with MSE 4.03 × 10-9. The system can recognize target patterns with a training accuracy of 99.82%. The test results of the ANN program identification system can detect myocardial ischemia and normal heart abnormalities with an accuracy of 86.7%. Some data were not detected because the ANN output did not meet the criteria for cardiac ischemia or normal myocardium on the ECG signal. Based on the accuracy of the ANN program identification system, the detection of myocardial ischemia rhythm ECG signal patterns using ANN can be said to work well.

Network pharmacology and molecular docking to explore Siraitia grosvenorii’s potential mechanism in preventing and treating proliferative diabetic retinopathy

Although Siraitia grosvenorii (abbreviated as S.g.) is frequently used to prevent and cure diabetes problems, the precise mechanism underlying its ability to do so remains unknown. Through network pharmacology and molecular docking techniques, we studied the early molecular mechanisms of S.g in the treating of proliferative diabetic retinopathy (PDR) in this study. The Traditional Chinese Medicine Systems Pharmacology (TCMSP) database was used to screen the active compounds and related targets of S.g. Oral bioavailability (OB) 30% and drug likeness (DL) 0.18 were used as screening criteria. The active compounds without knowledge of a probable target were excluded. The Uniprot database included converted symbols for the associated targets. GEO2R was used to explore several genes related to PDR. Using jvenn web service to intersect targets of S.g and PDR. The Xiantao Academic Online website was used to examine the expression patterns of intersect targets in PDR samples. The STRING database was used to create a protein-protein interaction (PPI) network of intersecting targets. Cytoscape software was used to show the PPI network, MCODE software was used to evaluate the network’s core proteins, and CytoHubba software was used to extract the important networks of the top three targets. Omicshare platform carried a functional analysis using the Gene Ontology (GO) and pathway enrichment analysis using the Kyoto Encyclopedia of Genes and Genomes (KEGG). Pymol, AutoDock Vina software, Schrödinger Software were used to conduct molecular docking experiments or pockets search on the top three targets. The results showed that 85 targets were matched to six active compounds of S.g. 18 intersect targets were found. Seven DEGs were up-regulated and eleven genes were down-regulated when these targets were divided into two groups. TNF, PTGS2, and CASP3 were the main targets, according to the PPI network. The intersect targets were mostly related to angiogenesis, cell proliferation, oxidative stress, inflammatory response, and metabolism. It was discovered that the core targets TNF, PTGS2, and CASP3 had various levels of affinity for their respective compounds. Interestingly, multiple good drug-forming pockets for CASP3 and PTGS2 targets were identified through Schrödinger software. In particular, six compounds bind to the top three core targets to inhibit IL-17 signaling pathway, AGE-RAGE signaling pathway in diabetic complications, Pathways in cancer and 14 other signaling pathways to inhibit inflammation, apoptosis, oxidative stress, arachidonic acid metabolism, and angiogenesis to prevent and treat PDR. The study’s findings, which served as a guide for the widespread use of S.g in PDR clinical practise, included multi-substances and targets of S.g to prevent and cure PDR.

Cellular reaction gene regulation network for swarm robots with pattern formation maneuvering control.

Self-organized pattern formation enables swarm robots to interact with local environments to self-organize into intricate structures generated by gene regulatory network (GRN) control methods without global knowledge. Previous studies have reported that it is challenging to maintain pattern formation stability during maneuvering in the environment due to local morphogenetic reaction rules. Motivated by the mechanism of the GRN in multi-cellular organisms, we propose a novel cellular reaction gene regulatory network (CR-GRN) for pattern formation maneuvering control. In CR-GRN, a cellular reaction network is creatively proposed to depict the robots, environment, virtual target pattern, and their interaction to generate emergent swarm behavior in multi-robot systems. A novel diffusion equation is proposed to simulate the process of morphogen diffusion among cells to ensure stable adaptive pattern generation. In addition, genes, proteins, and morphogens are used to define the internal and external states of cells and form a feedback regulation network. Simulation experiments are conducted to validate the proposed method. The results show that the CR-GRN can satisfy the requirements of turning curvature and maintain the robot's uniformity based on the proposed algorithm. This proves that robots using the CR-GRN can cooperate more effectively to cope in a complicated environment, and maintain a stable formation during maneuvering.

Hydrogel on a Smart Nanomaterial Interface to Carry Therapeutics for Digitalized Glioma Treatment.

Glioma is considered the primary brain tumor to cause brain illnesses, and it is difficult to treat and shows resistance to various routine therapeutics. The most common treatments to cure glioma are the surgical removal of tumors followed by adjuvant chemotherapy and radiation therapy. The latest biocompatible interfaces have been incorporated into therapeutic modalities such as the targeted delivery of drugs using hydrogels to treat and manage brain glioma. This review illustrates the applications of the multimodal hydrogel as the carrier of therapeutics, gene therapy, therapeutic tactics, and glioma devices. The scientific articles were retrieved from 2019 to 2022 on Google Scholar and the Scopus database and screened to determine whether they were suitable for review. The 20 articles that fit the study are summarized in this review. These studies indicated that the sizes of the hydrogel range from 28 nm to 500 nm. There are 16 out of 20 articles that also explain the post-surgical application of hydrogels, and 13 out of 20 articles are employed in 3D culture and other structural manifestations of hydrogels. The pros of the hydrogel include the quick formulation for a sufficient filling of irregular damage sites, solubilizing hydrophobic drugs, continuously slowing drug release, provision of a 3D cell growth environment, improving efficacy, targetability of soluble biomolecules, increasing patient compliance, and decreased side effects. The cons of the hydrogel include difficult real-time monitoring, genetic manipulations, the cumbersome synchronized release of components, and lack of safety data. The prospects of the hydrogel may include the development of electronic hydrogel sensors that can be used to enhance guidance for the precise targeting patterns using patient-specific pathological idiosyncrasies. This technology has the potential to revolutionize the precision medicine approaches that would aid in the early detection and management of solid brain tumors.

Poly I:C promotes malate to enhance innate immune response against bacterial infection

Polyinosinic-polycytidylic acid (poly I:C) is a synthetic analog of double-stranded RNA (dsRNA) that activates anti-infective innate immunity. The underlying mechanisms are identified as targeting pattern recognition receptors and Th1-inducing. However, whether poly I:C manipulates metabolism to implement this anti-infective function is unknown. Here, GC-MS based metabolomics was used to characterize metabolic profiles induced by different doses of poly I:C. Analysis on the dose-dependent metabolomes shows that elevation of the TCA cycle and malate with the increasing dose of ploy I:C forms the most characteristic feature of the poly I:C stimulation. Exogenous malate activates the TCA cycle and elevates survival of zebrafish infected with Vibrio alginolyticus, which is related to the elevated expression of il-1b, il-6, il-8, tnf-a, and c3b. These results reveal a previously unknown regulation of poly I:C that boosts the TCA cycle to enhance innate immunity against bacterial infection.

Molecular mechanism study of cancer treatment based on network pharmacology of lily

OBJECTIVE: To make predictions related to the treatment of cancer by lily. METHODS: A systematic study of the constituents, targets and pathways of lily and cancer treatment was conducted using network pharmacology and molecular docking methods. The active ingredients of lily were screened and selected for investigation using TCMSP, Uniprot and PubChem databases, and the "ingredient-target-pathway" correlation axis was established. PubChem was used to collect the compounds in lily, and the active ingredients and targets with OB≥30% and DL≥0.18 in lily were obtained using the TCMSP Chinese medicine database. The active ingredients that met the criteria were also screened, and the binding patterns of the core targets and active ingredients were verified using molecular docking techniques before the active ingredients in lily were genetically aligned using Uniprot, and the corresponding genes were collated. The genes of different cancers were collated using CTD. Cytoscape 3.9.0 was used to create a map of the active ingredients and their corresponding targets. Finally, the results obtained were used to make predictions related to the treatment of cancer in lily. Results: The herb-compound-target network was obtained through screening. After cross-matching the active targets of the chemical components in lily with various cancers, 42 intersecting targets were obtained. Conclusion: The rank values (degree) of the intersecting targets were analysed and six targets with a degree greater than 5 were found to be PTGS2 (12), MMP1 (10), PPARG (8), HSP90AA1 (8), TP53 (8) and ESR2 (6); the diseases that were closely linked to the targets were Cancer, unspecific (The findings of this paper may provide a reference for the development of relevant targeted drugs and targeted therapeutic approaches in the future.

Particularism or Policy? When Distributive Outlays Flow to the President’s Core Supporters

The literature on distributive politics reveals that presidents regularly influence federal spending and disproportionately direct federal grants toward their core supporters. This paper offers a comprehensive assessment of the interpretation of core-supporter targeting. Empirical evidence shows that the underlying patterns of partisan targeting do not accord with standard accounts of party-building activities nor electoral considerations that are evidence of presidential particularism. Instead, this paper argues that presidential policy priority better explains core-state targeting. Presidents use agencies that are ideologically aligned with them or associated with their policy priorities to enhance the largesse they bestow on core constituencies, and this is the consequence of presidents pursuing ideological and policy goals. Collectively, it indicates a less cynical point of view on the orientation of the American presidency.

A Robust, Highly Multiplexed Mass Spectrometry Assay to Identify SARS-CoV-2 Variants.

ABSTRACTSevere acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants are characterized by differences in transmissibility and response to therapeutics. Therefore, discriminating among them is vital for surveillance, infection prevention, and patient care. While whole-genome sequencing (WGS) is the “gold standard” for variant identification, molecular variant panels have become increasingly available. Most, however, are based on limited targets and have not undergone comprehensive evaluation. We assessed the diagnostic performance of the highly multiplexed Agena MassARRAY SARS-CoV-2 Variant Panel v3 to identify variants in a diverse set of 391 SARS-CoV-2 clinical RNA specimens collected across our health systems in New York City, USA and Bogotá, Colombia (September 2, 2020 to March 2, 2022). We demonstrated almost perfect levels of interrater agreement between this assay and WGS for 9 of 11 variant calls (κ ≥ 0.856) and 25 of 30 targets (κ ≥ 0.820) tested on the panel. The assay had a high diagnostic sensitivity (≥93.67%) for contemporary variants (e.g., Iota, Alpha, Delta, and Omicron [BA.1 sublineage]) and a high diagnostic specificity for all 11 variants (≥96.15%) and all 30 targets (≥94.34%) tested. Moreover, we highlighted distinct target patterns that could be utilized to identify variants not yet defined on the panel, including the Omicron BA.2 and other sublineages. These findings exemplified the power of highly multiplexed diagnostic panels to accurately call variants and the potential for target result signatures to elucidate new ones.IMPORTANCE The continued circulation of SARS-CoV-2 amid limited surveillance efforts and inconsistent vaccination of populations has resulted in the emergence of variants that uniquely impact public health systems. Thus, in conjunction with functional and clinical studies, continuous detection and identification are quintessential to informing diagnostic and public health measures. Furthermore, until WGS becomes more accessible in the clinical microbiology laboratory, the ideal assay for identifying variants must be robust, provide high resolution, and be adaptable to the evolving nature of viruses like SARS-CoV-2. Here, we highlighted the diagnostic capabilities of a highly multiplexed commercial assay to identify diverse SARS-CoV-2 lineages that circulated from September 2, 2020 to March 2, 2022 among patients seeking care in our health systems. This assay demonstrated variant-specific signatures of nucleotide/amino acid polymorphisms and underscored its utility for the detection of contemporary and emerging SARS-CoV-2 variants of concern.

A review of frequently used Kampo prescriptions part 1. Daikenchuto

AbstractBackgroundThe original formula name for daikenchuto (DKT) was written in ‘Jin Gui Yao Lue (Kinkiyōryaku in Japanese)’. DKT as used in Japan consists of four types of crude drug.Key findingsAlthough there are few examples of its use in Chinese classical records, it has begun to be used extensively in modern Japan for intestinal obstruction after laparotomy. Furthermore, to prove its usefulness, many clinical trials on DKT for intestinal obstruction have been conducted since the 1990s. Although the efficacy of DKT in preventing or improving intestinal obstruction was controversial, a meta‐analysis of nine studies reported in recent years showed that DKT significantly reduced the incidence of intestinal obstruction after gastrointestinal cancer surgery, suggesting its effectiveness. Related knowledge of irritable bowel syndrome has also been accumulated through case reports. DKT has been shown to be involved in the promotion of gastrointestinal motility, inhibition of excessive gastrointestinal motility, secretion of gastrointestinal hormones, and improvement of gastrointestinal blood flow, and to have anti‐inflammatory effects. In addition to drug rash, serious adverse events include hepatic dysfunction and interstitial pneumonia, but there have been relatively few reports.ConclusionDKT has been used in many cases in Japan, but it is often used without considering the ‘pattern (shō)’. Since it was originally formulated for the treatment of chills (hie), it would be more effective if its target (pattern) were taken into consideration. Overall, DKT is a safe prescription with a wide range of applications.

CPUE standardization for southern bluefin tuna (Thunnus maccoyii) in the Korean tuna longline fishery, accounting for spatiotemporal variation in targeting through data exploration and clustering.

Accounting for spatial and temporal variation in targeting is a concern in many catch per unit effort (CPUE) standardization exercises. In this study we standardized southern bluefin tuna (Thunnus maccoyii, SBT) CPUE from the Korean tuna longline fishery (1996–2018) using generalized linear models (GLMs) with operational set by set data. Data were first explored to investigate the operational characteristics of Korean tuna longline vessels fishing for SBT, such as the spatial and temporal distributions of effort, and changes in the nominal catch rates among major species and species composition. Then we estimated SBT CPUE by area used for the stock assessment in the CCSBT (Commission for the Conservation of Southern Bluefin Tuna) and identified two separate areas in which Korean tuna longline vessels have targeted SBT and albacore tuna (T. alalunga), with targeting patterns varying spatially, seasonally and longer term. We applied two approaches, data selection and cluster analysis of species composition, and compared their ability to address concerns about the changing patterns of targeting through time. Explanatory variables for the GLM analyses were year, month, vessel identifier, fishing location (5° cell), number of hooks, moon phase, and cluster. GLM results for each area suggested that location, year, targeting, and month effects were the principal factors affecting the nominal CPUE. The standardized CPUEs for both areas decreased until the mid-2000s and have shown an increasing trend since that time.

A hybrid approach to study large conformational transitions of biomolecules from single particle XFEL diffraction data.

X-ray free-electron laser (XFEL) is the latest generation of the X-ray source that could become an invaluable technique in structural biology. XFEL has ultrashort pulse duration, extreme peak brilliance, and high spatial coherence, which could enable the observation of the biological molecules in near nature state at room temperature without crystallization. However, for biological systems, due to their low diffraction power and complexity of sample delivery, experiments and data analysis are not straightforward, making it extremely challenging to reconstruct three-dimensional (3D) structures from single particle XFEL data. Given the current limitations to the amount and resolution of the data from such XFEL experiments, we propose a new hybrid approach for characterizing biomolecular conformational transitions by using a single 2D low-resolution XFEL diffraction pattern in combination with another known conformation. In our method, we represent the molecular structure with a coarse-grained model, the Gaussian mixture model, to describe large conformational transitions from low-resolution XFEL data. We obtain plausible 3D structural models that are consistent with the XFEL diffraction pattern by deforming an initial structural model to maximize the similarity between the target pattern and the simulated diffraction patterns from the candidate models. We tested the proposed algorithm on two biomolecules of different sizes with different complexities of conformational transitions, adenylate kinase, and elongation factor 2, using synthetic XFEL data. The results show that, with the proposed algorithm, we can successfully describe the conformational transitions by flexibly fitting the coarse-grained model of one conformation to become consistent with an XFEL diffraction pattern simulated from another conformation. In addition, we showed that the incident beam orientation has some effect on the accuracy of the 3D structure modeling and discussed the reasons for the inaccuracies for certain orientations. The proposed method could serve as an alternative approach for retrieving information on 3D conformational transitions from the XFEL diffraction patterns to interpret experimental data. Since the molecules are represented by Gaussian kernels and no atomic structure is needed in principle, such a method could also be used as a tool to seek initial models for 3D reconstruction algorithms.

Long-distance pattern projection through an unfixed multimode fiber with natural evolution strategy-based wavefront shaping.

Focusing light into an arbitrary pattern through complex media is desired in energy delivery-related scenarios and has been demonstrated feasible with the assistance of wavefront shaping. However, it still encounters challenges in terms of pattern fidelity and focusing contrast, especially in a noisy and perturbed environment. In this work, we show that the strategy relying on natural gradient ascent-based parameter optimization can help to resist noise and disturbance, enabling rapid wavefront optimization towards high-quality pattern projection through complex media. It is revealed that faster convergence and better robustness can be achieved compared with existing phase control algorithms. Meanwhile, a new fitness function based on cosine similarity is adopted for the algorithm, leading to higher focusing contrast without sacrificing similarity to the target pattern. As a result, long-distance projection of an arbitrary pattern can be accomplished with considerably enhanced performance through a 15-meter multimode fiber that is not fixed and susceptible to perturbation. With further engineering, the approach may find special interests for many biomedical applications, such as deep-tissue photon therapy and optogenetics, where free-space localized optical delivery encounters challenges.

4-bit adhesion logic enables universal multicellular interface patterning

Multicellular systems, from bacterial biofilms to human organs, form interfaces (or boundaries) between different cell collectives to spatially organize versatile functions1,2. The evolution of sufficiently descriptive genetic toolkits probably triggered the explosion of complex multicellular life and patterning3,4. Synthetic biology aims to engineer multicellular systems for practical applications and to serve as a build-to-understand methodology for natural systems5–8. However, our ability to engineer multicellular interface patterns2,9 is still very limited, as synthetic cell–cell adhesion toolkits and suitable patterning algorithms are underdeveloped5,7,10–13. Here we introduce a synthetic cell–cell adhesin logic with swarming bacteria and establish the precise engineering, predictive modelling and algorithmic programming of multicellular interface patterns. We demonstrate interface generation through a swarming adhesion mechanism, quantitative control over interface geometry and adhesion-mediated analogues of developmental organizers and morphogen fields. Using tiling and four-colour-mapping concepts, we identify algorithms for creating universal target patterns. This synthetic 4-bit adhesion logic advances practical applications such as human-readable molecular diagnostics, spatial fluid control on biological surfaces and programmable self-growing materials5–8,14. Notably, a minimal set of just four adhesins represents 4 bits of information that suffice to program universal tessellation patterns, implying a low critical threshold for the evolution and engineering of complex multicellular systems3,5.

Icy Targets in Karajá ATR Harmony as Contrast Preservation

This paper presents a novel application of Contrast Preservation (Lubowicz 2003) to analyze a puzzling pattern of icy targets (Jurgec 2011). Icy targets are segments which harmonize but then block the spread of harmony, and a particularly theoretically challenging type is present in Karajá, in which derived and underlying [+ATR] high vowels behave differently (Ribeiro 2002;2012). We show that this harmony pattern can be successfully analyzed by considering the behaviour of these icy targets as a form of contrast preservation, where high [-ATR] vowels must harmonize when followed by a [+ATR] vowel, but the underlying contrast between [-ATR] and [+ATR] high vowels is preserved on any preceding vowels. The icy target effect thus emerges as a way to compromise between the pressure to harmonize high vowels and the pressure to preserve underlying ATR contrasts in high vowels. In this way, we extend Contrast Preservation Theory to include vowel harmony patterns, opening new opportunities to analyze puzzling patterns as a choice in which contrasts to preserve.

Precise Pattern Alignment for Die-to-Database Inspection Based on the Generative Adversarial Network

Alignment between the reference layout (or target pattern) and the corresponding scanning electron microscope (SEM) image is a crucial task for the die-to-database (D2DB) inspection in the semiconductor industry. However, it is challenging to align them accurately because the style and quality of reference layouts represented as a computer-aided design (CAD) are quite different from those of grayscale SEM images with noise. Direct application of conventional cross-correlation-based matching methods often leads to misalignment. Here, we propose a new method enabling the precise pattern alignment. The main idea is to transform SEM images into target-like CAD images using a generative adversarial network (GAN). As the generated and real layout images have similar style and quality, they can be precisely aligned using conventional matching methods. Then, the SEM image can be located correctly on the corresponding reference layout for inspection. A polygon-based clustering algorithm for target patterns is developed to avoid manual selection and minimize the number of training data.

Automatic coloration of pattern based on color parsing of Sung porcelain

In order to improve the coloration efficiency of fashion design, an automatic color matching mechanism based on adaptive color clustering of image scenes is proposed for clothing patterns. Taking images of Sung porcelain as an example, 300 porcelain images from six different kilns were collected as testing samples. The porcelain area of each sample image was detected by image segmentation and denoising. The bipartite K-means clustering algorithm was utilized to adaptively extract the main colors of each sample. Also, the secondary clustering was carried out to obtain the main color values, proportions and co-occurrence ratios of each kiln’s image. A dynamic color matching mechanism integrating the number of color clusters, co-occurrence ratio, and structure characteristics of the target pattern, was designed and automatic color parsing and matching software was developed. The experiment results show that the color matching control parameters, source images, pattern shape, and other factors affect the main color selection sequence and the final matching effect. The time consumed for single sample color extraction and pattern automatic color matching are all less than 1 s, which can quickly realize the pattern color migration based on image scenes and further provide auxiliary decision-making for clothing pattern color design.

Investigating the origins of bacterial SERS responses to antibiotics observed in the extracellular matrix liquid

Surface-enhanced Raman spectroscopy (SERS) has been applied to analyze bacterial cells and their responses to antibiotic exposure. However, significant knowledge gaps remain regarding the origins of specific antibiotic response patterns and the necessary experimental steps required to see them clearly in the SERS spectra, particularly involving SERS responses observed in the extracellular matrix liquid of bacterial samples. In this study, a variety of experimental parameters were tested to assess the antibiotic response patterns seen in liquid samples from E. coli under different conditions. These include testing the impact of washing the cells with water after incubating them with antibiotics, as well as the effect of using different types of liquids with varying characteristics for incubating the bacteria with the antibiotics. It was found that the experimental procedure has a significant impact on the resulting SERS signals, and the target patterns could only be observed in specific conditions. In particular, the step of washing the bacteria with water is necessary for observing the antibiotic response patterns, and incubating the bacteria and antibiotics in a nutrient-rich growth medium is preferable to incubating the cells in a buffer or in distilled water. These findings can be used to improve existing methods for testing antibiotic responses with SERS, and could potentially help to further develop and optimize SERS-based procedures for assessing antibiotic sensitivity.

A soft-computing based approach to overlapped cells analysis in histopathology images with genetic algorithm

Deep learning methods have shown great significance for medical image processing in recent years, including radiography, magnetic resonance imaging, nuclear medicine, and histopathology. Learning-based methods help to detect the target patterns when the network is well-trained. However, the gap between detected patterns and clinical decisions is still enormous, and soft-computing methods could help to improve the decisions based on the specific features of the problem. In this paper, the target is to detect the immunohistochemistry (IHC) positive cells in lymphoma histopathology images. We use a deep learning network to detect the positive cells in pixel level, and results show the proposed residual U-Net structure outperforms the baseline models. In the failure cases, they mainly occur when two cells are overlapped in predicted masks, which is the drawback of learning-based methods. Hence, a soft-computing based method is proposed to use ellipse formulation to represent a cellular pattern, and use genetic algorithm (GA) to determine an optimal decision of overlapped ellipses. We use two datasets: 36 images with ground truth from pathologists’ annotation, and 43 images with overlapped cells (cropped from failed predictions). A series of experiments show that the proposed deep learning model could detect most of IHC-positive cells in the proposed dataset, and our soft-computing method could detect 86.04% of the overlapped cells and the proposed GA outperforms the baseline methods.